© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 3276
    Prev
    Next
    INDEX
    Explanations

    instructions for baking and cooking recipes, specifically focusing on ingredients and procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    ingredients and their measurements in cooking contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vu
    -0.71
     Exile
    -0.67
    vernment
    -0.66
    NEY
    -0.64
     outing
    -0.62
     Paran
    -0.61
     Judicial
    -0.60
    igators
    -0.60
     Directorate
    -0.59
     Rivers
    -0.59
    POSITIVE LOGITS
    cream
    1.65
    cup
    1.22
    fat
    1.19
    cloth
    1.17
    flies
    1.16
    knife
    1.16
    fing
    1.15
    finger
    1.13
    beer
    1.12
    beans
    1.00
    Activations Density 0.040%

    No Known Activations